AI, Software & Cloud Architect
Jose Quesada
I lead the architecture of AI-native and agentic systems, and of the cloud, software, and security platforms they depend on.
SWAT Team Manager at SOIN, leading the team behind the company's most complex initiatives across AI, cloud and infrastructure, architecture, modernization, and innovation — from new agent platforms to production-critical systems.
Building enterprise systems since 2015Costa Rica
- Agentic AI
- AI-Native Engineering
- Cloud & Kubernetes
- Software Architecture
- Security
- Technical Leadership
Core expertise
See all seven domains- AI & Agentic Systems
- Architecture for production AI: agent runtimes, retrieval, model routing, tools, memory, gateways, evaluation, and the enterprise systems they connect to.
- AI-Native Software Engineering
- Redesigning the software delivery lifecycle around coding agents, specifications, automated verification, and human judgment.
- Cloud & Platform Engineering
- Cloud and infrastructure architecture across AWS, OCI, and Azure: Kubernetes, gateways, networking, observability, and infrastructure as code.
- Engineering Leadership
- Leading complex technical initiatives, setting architectural direction, developing engineers, and turning experimentation into repeatable engineering practice.
Selected work
An agent platform for enterprise systems
A shared platform for building and operating enterprise AI agents, with provider abstraction, governed tool access, tenant isolation, secure credentials, and end-to-end observability.
A platform that generates applications from specifications
AI code generation for enterprise delivery, built around a knowledge repository, deterministic generation, reviewable plans, and human judgment.
A mobile app that turns speech into structured data
A cross-platform field app where the primary input is a person talking, and an AI service behind it turns what they said into validated, structured records.
Current focus
AI & agentic systems
Designing enterprise agent platforms, RAG systems, tool architectures, and multi-model runtimes that integrate with existing business systems. MCP is settling into that picture; A2A I am watching closely.
AI-native software engineering
Redesigning how software is specified, built, reviewed, tested, and modernized when coding agents join the engineering workflow.
Cloud & infrastructure
Building the cloud and platform layers behind modern AI systems: Kubernetes, gateways, infrastructure as code, observability, networking, and multi-cloud architecture.
Engineering leadership & innovation
Leading SWAT, turning emerging technologies into repeatable engineering capability, and guiding teams through high-complexity technical work.
Security & AI governance
Designing identity, credential boundaries, tenant isolation, guardrails, auditability, and human control into AI systems from the beginning.
Software architecture & modernization
Modernizing complex enterprise systems and integration-heavy platforms while preserving the business behavior, reliability, and operational control they already provide.
Featured credentials
View all certificationsAgentic AI Business Solutions Architect
Microsoft

Machine Learning Engineer – Associate
Amazon Web Services (AWS)
Azure AI Engineer Associate
Microsoft

DevOps Engineer – Professional
Amazon Web Services (AWS)

Security – Specialty
Amazon Web Services (AWS)
DevOps Engineer Expert
Microsoft
Power Platform Solution Architect Expert
Microsoft

Developer – Associate
Amazon Web Services (AWS)
Writing
August 30, 2026
From Software Engineering to AI-Native Engineering
AI did not make software engineering faster. It moved the bottleneck from writing code to deciding whether the code is correct — and I found that out by pointing an agent at my own site.
Beyond the work
I live in Costa Rica and I am a solo parent to two kids, nine and seven. Most of my time outside work belongs to them: hiking, zip-lining, horseback riding, whatever adventure comes next. I play golf and soccer, study Japanese, travel whenever I can, and watch a lot of anime. Tensura is the easy favorite.
Beyond the work









